Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extract
    -0.08
    +(
    -0.07
    قسام
    -0.07
    🧭
    -0.07
    createCommand
    -0.07
     גם
    -0.07
     Seamless
    -0.07
    ].'
    -0.06
     insert
    -0.06
    枫
    -0.06
    POSITIVE LOGITS
    ervative
    0.07
     embodiments
    0.07
     Bund
    0.07
    _likelihood
    0.07
    akov
    0.07
    ズ
    0.07
    .bs
    0.07
    _GO
    0.07
     Bro
    0.06
    죔
    0.06
    Act Density 0.001%

    No Known Activations